A novel adaptive fault detection methodology for complex system using deep belief networks and multiple models: A case study on cryogenic propellant loading system

Ren, Hao; Chai, Yi; Qu, Jianfeng; Ye, Xin; Tang, Qiu

doi:10.1016/j.neucom.2017.10.063

Cited by 44 publications

(16 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, a vector is generated in the visible layer of the first RBM, and then the value is passed to the hidden layer through the RBM network, after which the visible layer is used to reconstruct the visible layer. The weight between the hidden layer and the visible layer is updated according to the difference between the reconstructed layer and the visible layer, until the maximum number of iterations is reached [36]. After the unsupervised training is completed, the deep belief network is supervised by adding tag data at the top of the deep belief network.…”

Section: Dbn Trainingmentioning

confidence: 99%

An Improved Parallel MDBN With AVMD for Nonlinear System Modeling

Jin

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Nonlinear system modeling using Deep Belief Network (DBN) is currently a research hotspot. However, the training process of DBN needs large amount of data to guarantee accuracy, and the traditional DBN may not meet the requirement of high-precision modeling. In this paper, we first improve the original DBN and Variational Mode Decomposition (VMD) algorithms, and on this basis, we then proposed a parallel Momentum Deep Belief Networks (MDBN) with Adaptive Variational Mode Decomposition (AVMD). Parallel AVMD-MDBN is an improved modeling method based on the deep learning model DBN. Firstly, a single raw dataset is decomposed into a specific number of sub-datasets using AVMD. Then these subdatasets are distributed among a number of improved MDBNs. A single raw dataset learning model and algorithm is extended to multiple feature extraction nodes to learn the characteristics of multiple subdatasets in parallel. Finally, the results of the multiple nodes are transmitted to the main feature extraction node to complete the regression calculation. In order to verify the effectiveness of the model, the proposed parallel AVMD-MDBN model is tested on a nonlinear dynamic system modeling, a Mackey-Glass timeseries prediction and a financial stock prediction. Our experimental results show that the proposed parallel AVMD-MDBN has better performances in terms of improving feature learning ability than that of other methods. INDEX TERMS Parallel momentum deep belief networks, adaptive variational mode decomposition, contrast divergence algorithm, nonlinear system modeling, financial stock prediction.

show abstract

Section: Dbn Trainingmentioning

confidence: 99%

An Improved Parallel MDBN With AVMD for Nonlinear System Modeling

Jin

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Most of these studies combined two of these methods or combined them with multiple perceptron models to realize feature extraction and fault classification. Hao et al [21] developed an approach based on deep belief networks and multiple models (DBNs-MMs) to describe the nonlinearity and complexity of interacting dynamic systems. They also designed an adaptive threshold method to detect the faults with the residuals obtained from the outputs of DBNs-MMs.…”

Section: Literature Reviewmentioning

confidence: 99%

Progressive Improved Convolutional Neural Network for Avionics Fault Diagnosis

Chen

Jing

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Among deep learning methods, convolutional neural networks (CNNs) are able to extract features automatically and have increasingly been used in intelligent fault diagnosis studies. However, studies seldomly concentrate on the weakness associated with a highly imbalanced distribution of fault types due to different failure rates and when multiple faults are easily confused with single faults. To solve these problems, this paper developed a stochastic discrete-time series deep convolutional neural network (SDCNN) method based on random oversampling along with a progressive method with multiple SDCNNs to improve the diagnosis performance. To assess the developed method, datasets from three avionics 24-pulse autotransformer rectifier units (ATRUs), which are secondary electric power supplies in aircraft, were analyzed and compared with other CNN methods. INDEX TERMS Fault diagnosis, convolutional neural network, imbalanced classification, confusable fault types.

show abstract

“…Compared with shallow neural network methods, DBNs can capture complex nonlinear features, have a powerful modeling capacity and are quite suitable for modeling complex SCADA data [22]. DBNs have received attention in the fields of wind speed prediction [23], mechanical engineering fault diagnosis [24] and complex system fault detection [25]. The performance of DBNs is largely dependent on their structural parameters.…”

Section: Introductionmentioning

confidence: 99%

Early Fault Detection of Wind Turbines Based on Operational Condition Clustering and Optimized Deep Belief Network Modeling

Wang¹,

Wang²,

Jiang³

et al. 2019

Energies

View full text Add to dashboard Cite

Health monitoring and early fault detection of wind turbines have attracted considerable attention due to the benefits of improving reliability and reducing the operation and maintenance costs of the turbine. However, dynamic and constantly changing operating conditions of wind turbines still pose great challenges to effective and reliable fault detection. Most existing health monitoring approaches mainly focus on one single operating condition, so these methods cannot assess the health status of turbines accurately, leading to unsatisfactory detection performance. To this end, this paper proposes a novel general health monitoring framework for wind turbines based on supervisory control and data acquisition (SCADA) data. A key feature of the proposed framework is that it first partitions the turbine operation into multiple sub-operation conditions by the clustering approach and then builds a normal turbine behavior model for each sub-operation condition. For normal behavior modeling, an optimized deep belief network is proposed. This optimized modeling method can capture the sophisticated nonlinear correlations among different monitoring variables, which is helpful to enhance the prediction performance. A case study of main bearing fault detection using real SCADA data is used to validate the proposed approach, which demonstrates its effectiveness and advantages.

show abstract

A novel adaptive fault detection methodology for complex system using deep belief networks and multiple models: A case study on cryogenic propellant loading system

Cited by 44 publications

References 39 publications

An Improved Parallel MDBN With AVMD for Nonlinear System Modeling

An Improved Parallel MDBN With AVMD for Nonlinear System Modeling

Progressive Improved Convolutional Neural Network for Avionics Fault Diagnosis

Early Fault Detection of Wind Turbines Based on Operational Condition Clustering and Optimized Deep Belief Network Modeling

Contact Info

Product

Resources

About